SCOPE:Planning for Hybrid Querying over Clinical Trial Data
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913079274504192 |
|---|---|
| author | Chowdhury, Suparno Roy Choudhury, Manan Roy Anvekar, Tejas Khan, Muhammad Ali Khakwani, Kaneez Zahra Rubab Sonbol, Mohamad Bassam Riaz, Irbaz Bin Gupta, Vivek |
| author_facet | Chowdhury, Suparno Roy Choudhury, Manan Roy Anvekar, Tejas Khan, Muhammad Ali Khakwani, Kaneez Zahra Rubab Sonbol, Mohamad Bassam Riaz, Irbaz Bin Gupta, Vivek |
| contents | We study clinical trial table reasoning, where answers are not directly stored in visible cells but must be reasoned from semantic understanding through normalization, classification, extraction, or lightweight domain reasoning. Motivated by the observation that current LLM approaches often suffer from "bad reasoning" under implicit planning assumptions, we focus on settings in which the model must recover implicit attributes such as therapy type, added agents, endpoint roles, or follow-up status from partially observed clinical-trial tables. We propose SCOPE (Structured Clinical hybrid Planning for Evidence retrieval in clinical trials), a multi-LLM planner-based framework that decomposes the task into row selection, structured planning, and execution. The planner makes the source field, reasoning rules, and output constraints explicit before answer generation, reducing ambiguity relative to direct prompting. We evaluate SCOPE on 1,500 hybrid reasoning questions over oncology clinical-trial tables against zero-shot, few-shot, chain-of-thought, TableGPT2, Blend-SQL, and EHRAgent. Results show that explicit multi-LLM planning improves accuracy for reasoning-based questions while offering a stronger accuracy-efficiency tradeoff than heavier agentic baselines. Our findings position clinical trial reasoning as a distinct table understanding problem and highlight hybrid planner-based decomposition as an effective solution |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25120 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SCOPE:Planning for Hybrid Querying over Clinical Trial Data Chowdhury, Suparno Roy Choudhury, Manan Roy Anvekar, Tejas Khan, Muhammad Ali Khakwani, Kaneez Zahra Rubab Sonbol, Mohamad Bassam Riaz, Irbaz Bin Gupta, Vivek Computation and Language We study clinical trial table reasoning, where answers are not directly stored in visible cells but must be reasoned from semantic understanding through normalization, classification, extraction, or lightweight domain reasoning. Motivated by the observation that current LLM approaches often suffer from "bad reasoning" under implicit planning assumptions, we focus on settings in which the model must recover implicit attributes such as therapy type, added agents, endpoint roles, or follow-up status from partially observed clinical-trial tables. We propose SCOPE (Structured Clinical hybrid Planning for Evidence retrieval in clinical trials), a multi-LLM planner-based framework that decomposes the task into row selection, structured planning, and execution. The planner makes the source field, reasoning rules, and output constraints explicit before answer generation, reducing ambiguity relative to direct prompting. We evaluate SCOPE on 1,500 hybrid reasoning questions over oncology clinical-trial tables against zero-shot, few-shot, chain-of-thought, TableGPT2, Blend-SQL, and EHRAgent. Results show that explicit multi-LLM planning improves accuracy for reasoning-based questions while offering a stronger accuracy-efficiency tradeoff than heavier agentic baselines. Our findings position clinical trial reasoning as a distinct table understanding problem and highlight hybrid planner-based decomposition as an effective solution |
| title | SCOPE:Planning for Hybrid Querying over Clinical Trial Data |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.25120 |